{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CQLSAIU4P6RBNR4XXNMUTP6GSP","short_pith_number":"pith:CQLSAIU4","schema_version":"1.0","canonical_sha256":"141720229c7fa216c797bb5949bfc693e695af57d0f420d8895a3d36ef02b2a6","source":{"kind":"arxiv","id":"2606.07068","version":1},"attestation_state":"computed","paper":{"title":"Bias in Filter Feature Selection Evaluation: A Meta-Analysis of Datasets, Baselines, and Experimental Design Choices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Malick Ebiele, Malika Bendechache, Rob Brennan","submitted_at":"2026-06-05T09:06:56Z","abstract_excerpt":"Background: Since 1990 many feature selection methods have been proposed across heterogeneous applications. To validate the usefulness of a new method, it needs to be compared against at least one baseline method from the existing literature on a feature selection task using at least one dataset. Recent developments in tabular Deep Learning (DL) and data valuation in Machine Learning (ML) suggest that the evaluation of new methods, algorithms, and models may be consciously or unconsciously biased. We hypothesise that a similar trend exists in feature selection (FS), particularly in filter feat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.07068","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T09:06:56Z","cross_cats_sorted":[],"title_canon_sha256":"451528026a0ba17ceacda7baa72ff7044cc1d3e68b3c31cfb138cee05eb6c54e","abstract_canon_sha256":"9036c15da88a8c7aefc76bcede5803c918ea2b31e93f52ea28c812e496dc2b07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:44.288202Z","signature_b64":"MPTHi23+0T34J1zIKavfAo/IbhgHO3t9Nzz2Gk0NqE2v+w69iJFbst6zf4YkrsvQ5JTPWo/WaL/n5ugnQui8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"141720229c7fa216c797bb5949bfc693e695af57d0f420d8895a3d36ef02b2a6","last_reissued_at":"2026-06-08T01:04:44.287240Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:44.287240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bias in Filter Feature Selection Evaluation: A Meta-Analysis of Datasets, Baselines, and Experimental Design Choices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Malick Ebiele, Malika Bendechache, Rob Brennan","submitted_at":"2026-06-05T09:06:56Z","abstract_excerpt":"Background: Since 1990 many feature selection methods have been proposed across heterogeneous applications. To validate the usefulness of a new method, it needs to be compared against at least one baseline method from the existing literature on a feature selection task using at least one dataset. Recent developments in tabular Deep Learning (DL) and data valuation in Machine Learning (ML) suggest that the evaluation of new methods, algorithms, and models may be consciously or unconsciously biased. We hypothesise that a similar trend exists in feature selection (FS), particularly in filter feat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07068","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.07068/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.07068","created_at":"2026-06-08T01:04:44.287416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07068v1","created_at":"2026-06-08T01:04:44.287416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07068","created_at":"2026-06-08T01:04:44.287416+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQLSAIU4P6RB","created_at":"2026-06-08T01:04:44.287416+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQLSAIU4P6RBNR4X","created_at":"2026-06-08T01:04:44.287416+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQLSAIU4","created_at":"2026-06-08T01:04:44.287416+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQLSAIU4P6RBNR4XXNMUTP6GSP","json":"https://pith.science/pith/CQLSAIU4P6RBNR4XXNMUTP6GSP.json","graph_json":"https://pith.science/api/pith-number/CQLSAIU4P6RBNR4XXNMUTP6GSP/graph.json","events_json":"https://pith.science/api/pith-number/CQLSAIU4P6RBNR4XXNMUTP6GSP/events.json","paper":"https://pith.science/paper/CQLSAIU4"},"agent_actions":{"view_html":"https://pith.science/pith/CQLSAIU4P6RBNR4XXNMUTP6GSP","download_json":"https://pith.science/pith/CQLSAIU4P6RBNR4XXNMUTP6GSP.json","view_paper":"https://pith.science/paper/CQLSAIU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07068&json=true","fetch_graph":"https://pith.science/api/pith-number/CQLSAIU4P6RBNR4XXNMUTP6GSP/graph.json","fetch_events":"https://pith.science/api/pith-number/CQLSAIU4P6RBNR4XXNMUTP6GSP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQLSAIU4P6RBNR4XXNMUTP6GSP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQLSAIU4P6RBNR4XXNMUTP6GSP/action/storage_attestation","attest_author":"https://pith.science/pith/CQLSAIU4P6RBNR4XXNMUTP6GSP/action/author_attestation","sign_citation":"https://pith.science/pith/CQLSAIU4P6RBNR4XXNMUTP6GSP/action/citation_signature","submit_replication":"https://pith.science/pith/CQLSAIU4P6RBNR4XXNMUTP6GSP/action/replication_record"}},"created_at":"2026-06-08T01:04:44.287416+00:00","updated_at":"2026-06-08T01:04:44.287416+00:00"}